Update PricePredict.py

PricePredict.py

@@ -26,9 +26,21 @@ sns.distplot(data_train['SalePrice'])
 #skewness and kurtosis 峰度和偏度
 print("Skewness: %f" % data_train['SalePrice'].skew())
 print("Kurtosis: %f" % data_train['SalePrice'].kurt())
+# CentralAir
+var = 'CentralAir'
+data = pd.concat([data_train['SalePrice'], data_train[var]], axis=1)
+fig = sns.boxplot(x=var, y="SalePrice", data=data)
+fig.axis(ymin=0, ymax=800000);
+# OverallQual
+var = 'OverallQual'
+data = pd.concat([data_train['SalePrice'], data_train[var]], axis=1)
+fig = sns.boxplot(x=var, y="SalePrice", data=data)
+fig.axis(ymin=0, ymax=800000);
+plt.show()
 corrmat = data_train.corr()
 f, ax = plt.subplots(figsize=(20, 9))
 sns.heatmap(corrmat, vmax=0.8, square=True)
+#plt.show()
 k  = 10 # 关系矩阵中将显示10个特征,由此我们可以知道相关性高的数据类别，便于后续的分析
 cols = corrmat.nlargest(k, 'SalePrice')['SalePrice'].index
 cm = np.corrcoef(data_train[cols].values.T)
@@ -38,7 +50,7 @@ hm = sns.heatmap(cm, cbar=True, annot=True, \
 sns.set()
 cols = ['SalePrice','OverallQual','GrLivArea', 'GarageCars','TotalBsmtSF', 'FullBath', 'TotRmsAbvGrd', 'YearBuilt']
 sns.pairplot(data_train[cols], size = 2.5)
-
+#plt.show()
 # 获取数据
 cols = ['OverallQual','GrLivArea', 'GarageCars','TotalBsmtSF', 'FullBath', 'TotRmsAbvGrd', 'YearBuilt']
 x = data_train[cols].values